You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
TensorLayer is a novel TensorFlow-based deep learning and reinforcement learning library designed for researchers and engineers. It provides an extensive collection of customizable neural layers to build complex AI models. TensorLayer is awarded the 2017 Best Open Source Software by the [ACM Multimedia Society](https://twitter.com/ImperialDSI/status/923928895325442049).
34
24
TensorLayer can also be found at [iHub](https://code.ihub.org.cn/projects/328) and [Gitee](https://gitee.com/organizations/TensorLayer).
35
25
36
26
# News
37
27
38
-
🔥📰🔥 Reinforcement Learning Model Zoos: [Low-level APIs for Research](https://github.com/tensorlayer/tensorlayer/tree/master/examples/reinforcement_learning) and [High-level APIs for Production](https://github.com/tensorlayer/RLzoo)
39
-
40
-
🔥📰🔥 [Sipeed Maxi-EMC](https://github.com/sipeed/Maix-EMC): Run TensorLayer models on the **low-cost AI chip** (e.g., K210) (Alpha Version)
28
+
🔥 Reinforcement Learning Model Zoo: [Low-level APIs for Research](https://github.com/tensorlayer/tensorlayer/tree/master/examples/reinforcement_learning) and [High-level APIs for Production](https://github.com/tensorlayer/RLzoo)
41
29
42
-
🔥📰🔥 [NNoM](https://github.com/majianjia/nnom): Run TensorLayer quantized models on the **MCU** (e.g., STM32) (Coming Soon)
30
+
🔥[Sipeed Maxi-EMC](https://github.com/sipeed/Maix-EMC): Run TensorLayer models on the **low-cost AI chip** (e.g., K210) (Alpha Version)
43
31
32
+
<!-- 🔥 [NNoM](https://github.com/majianjia/nnom): Run TensorLayer quantized models on the **MCU** (e.g., STM32) (Coming Soon) -->
44
33
45
-
🔥📰🔥[Free GPU and Data Storage from SurgicalAI](https://github.com/fangde/FreeGPU): SurgicalAI is sponsoring the TensorLayer Community with Cloud Computing Resources such as Free GPUs and Data Storage.
34
+
🔥 [Free GPU and storage resources](https://github.com/fangde/FreeGPU): TensorLayer users can access to free GPU and storage resources donated by SurgicalAI. Thank you SurgicalAI!
46
35
47
-
# Features
36
+
# Design Features
48
37
49
-
As deep learning practitioners, we have been looking for a library that can address various development
50
-
purposes. This library is easy to adopt by providing diverse examples, tutorials and pre-trained models.
51
-
Also, it allow users to easily fine-tune TensorFlow; while being suitable for production deployment. TensorLayer aims to satisfy all these purposes. It has three key features:
38
+
TensorLayer is a new deep learning library designed with simplicity, flexibility and high-performance in mind.
52
39
53
-
-**_Simplicity_** : TensorLayer lifts the low-level dataflow interface of TensorFlow to _high-level_ layers / models. It is very easy to learn through the rich [example codes](https://github.com/tensorlayer/awesome-tensorlayer) contributed by a wide community.
54
-
-**_Flexibility_** : TensorLayer APIs are transparent: it does not mask TensorFlow from users; but leaving massive hooks that help _low-level tuning_ and _deep customization_.
55
-
-**_Zero-cost Abstraction_** : TensorLayer can achieve the _full power_ of TensorFlow. The following table shows the training speeds of [VGG16](http://www.robots.ox.ac.uk/~vgg/research/very_deep/) using TensorLayer and native TensorFlow on a TITAN Xp.
56
-
57
-
| Mode | Lib | Data Format | Max GPU Memory Usage(MB) | Max CPU Memory Usage(MB) | Avg CPU Memory Usage(MB) | Runtime (sec) |
-***Simplicity*** : TensorLayer has a high-level layer/model abstraction which is effortless to learn. You can learn how deep learning can benefit your AI tasks in minutes through the massive [examples](https://github.com/tensorlayer/awesome-tensorlayer).
41
+
-***Flexibility*** : TensorLayer APIs are transparent and flexible, inspired by the emerging PyTorch library. Compared to the Keras abstraction, TensorLayer makes it much easier to build and train complex AI models.
42
+
-***Zero-cost Abstraction*** : Though simple to use, TensorLayer does not require you to make any compromise in the performance of TensorFlow (Check the following benchmark section for more details).
64
43
44
+
TensorLayer stands at a unique spot in the TensorFlow wrappers. Other wrappers like Keras and TFLearn
45
+
hide many powerful features of TensorFlow and provide little support for writing custom AI models. Inspired by PyTorch, TensorLayer APIs are simple, flexible and Pythonic,
46
+
making it easy to learn while being flexible enough to cope with complex AI tasks.
47
+
TensorLayer has a fast-growing community. It has been used by researchers and engineers all over the world, including those from Peking University,
48
+
Imperial College London, UC Berkeley, Carnegie Mellon University, Stanford University, and companies like Google, Microsoft, Alibaba, Tencent, Xiaomi, and Bloomberg.
65
49
50
+
# Multilingual Documents
66
51
67
52
TensorLayer has extensive documentation for both beginners and professionals. The documentation is available in
68
53
both English and Chinese.
@@ -74,17 +59,17 @@ both English and Chinese.
74
59
If you want to try the experimental features on the the master branch, you can find the latest document
You can find a large collection of tutorials, examples and real-world applications using TensorLayer within [examples](examples/)or through the following space:
64
+
You can find a large collection of examples that use TensorLayer in [here](examples/)and the following space:
The following table shows the training speeds of [VGG16](http://www.robots.ox.ac.uk/~vgg/research/very_deep/) using TensorLayer and native TensorFlow on a TITAN Xp.
161
144
@@ -167,13 +150,25 @@ The following table shows the training speeds of [VGG16](http://www.robots.ox.ac
0 commit comments